submission_id: rochatai-llama3-8b-cn-ro_9773_v2
developer_uid: Meliodia
best_of: 8
celo_rating: 1158.09
display_name: nitral-ai-hathor-l3-8b-v02
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 45, 'presence_penalty': 0.05, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
is_internal_developer: True
language_model: RochatAI/llama3-8B-cn-rochat-v1
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: RochatAI/llama3-8B-cn-ro
model_name: nitral-ai-hathor-l3-8b-v02
model_num_parameters: 8030261248.0
model_repo: RochatAI/llama3-8B-cn-rochat-v1
model_size: 8B
num_battles: 20993
num_wins: 9642
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-06-29T04:20:43+00:00
us_pacific_date: 2024-06-28
win_ratio: 0.4592959557947887
Resubmit model
Running pipeline stage MKMLizer
Starting job with name rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer
Waiting for job on rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer to finish
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║     _____            __           __                                ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║       /___/                                                         ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║                                                                     ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║                                                                     ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  belonging to:                                                      ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║                                                                     ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ║                                                                     ║
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer:   warnings.warn(warning_message, FutureWarning)
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Downloaded to shared memory in 21.849s
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: quantizing model to /dev/shm/model_cache
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:02, 135.12it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:03, 80.42it/s] 
Loading 0:  15%|█▌        | 44/291 [00:00<00:02, 105.02it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 92.19it/s] 
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 102.83it/s]
Loading 0:  32%|███▏      | 94/291 [00:00<00:01, 118.68it/s]
Loading 0:  37%|███▋      | 107/291 [00:01<00:02, 90.84it/s]
Loading 0:  42%|████▏     | 122/291 [00:01<00:01, 100.98it/s]
Loading 0:  49%|████▉     | 142/291 [00:01<00:01, 97.17it/s] 
Loading 0:  54%|█████▍    | 157/291 [00:01<00:01, 105.60it/s]
Loading 0:  60%|██████    | 175/291 [00:01<00:00, 118.70it/s]
Loading 0:  65%|██████▍   | 188/291 [00:01<00:01, 95.75it/s] 
Loading 0:  70%|██████▉   | 203/291 [00:01<00:00, 105.08it/s]
Loading 0:  76%|███████▌  | 221/291 [00:02<00:00, 122.15it/s]
Loading 0:  81%|████████  | 235/291 [00:02<00:00, 95.81it/s] 
Loading 0:  86%|████████▌ | 250/291 [00:02<00:00, 106.99it/s]
Loading 0:  90%|█████████ | 263/291 [00:02<00:00, 92.88it/s] 
Loading 0:  95%|█████████▍| 275/291 [00:02<00:00, 96.58it/s]
Loading 0: 100%|██████████| 291/291 [00:07<00:00,  8.65it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: quantized model in 23.092s
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Processed model RochatAI/llama3-8B-cn-rochat-v1 in 47.498s
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rochatai-llama3-8b-cn-ro-9773-v2
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rochatai-llama3-8b-cn-ro-9773-v2/tokenizer_config.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rochatai-llama3-8b-cn-ro-9773-v2/special_tokens_map.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rochatai-llama3-8b-cn-ro-9773-v2/tokenizer.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rochatai-llama3-8b-cn-ro-9773-v2/config.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rochatai-llama3-8b-cn-ro-9773-v2/flywheel_model.0.safetensors
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer:   warnings.warn(
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer:   warnings.warn(
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer:   warnings.warn(
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer:   return self.fget.__get__(instance, owner)()
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Saving duration: 0.403s
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.983s
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: creating bucket guanaco-reward-models
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/special_tokens_map.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/config.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/tokenizer_config.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/merges.txt
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/vocab.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/tokenizer.json
rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/rochatai-llama3-8b-cn-ro-9773-v2_reward/reward.tensors
Job rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer completed after 73.29s with status: succeeded
Stopping job with name rochatai-llama3-8b-cn-ro-9773-v2-mkmlizer
Pipeline stage MKMLizer completed in 74.16s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service rochatai-llama3-8b-cn-ro-9773-v2
Waiting for inference service rochatai-llama3-8b-cn-ro-9773-v2 to be ready
Inference service rochatai-llama3-8b-cn-ro-9773-v2 ready after 40.170856952667236s
Pipeline stage ISVCDeployer completed in 46.93s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0942931175231934s
Received healthy response to inference request in 1.2162110805511475s
Received healthy response to inference request in 1.2403826713562012s
Received healthy response to inference request in 1.3062264919281006s
Received healthy response to inference request in 1.2127115726470947s
5 requests
0 failed requests
5th percentile: 1.2134114742279052
10th percentile: 1.2141113758087159
20th percentile: 1.215511178970337
30th percentile: 1.2210453987121581
40th percentile: 1.2307140350341796
50th percentile: 1.2403826713562012
60th percentile: 1.2667201995849608
70th percentile: 1.2930577278137207
80th percentile: 1.4638398170471192
90th percentile: 1.7790664672851564
95th percentile: 1.9366797924041748
99th percentile: 2.0627704524993895
mean time: 1.4139649868011475
Pipeline stage StressChecker completed in 7.98s
rochatai-llama3-8b-cn-ro_9773_v2 status is now deployed due to DeploymentManager action
rochatai-llama3-8b-cn-ro_9773_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of rochatai-llama3-8b-cn-ro_9773_v2
Running pipeline stage ISVCDeleter
Checking if service rochatai-llama3-8b-cn-ro-9773-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 3.96s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key rochatai-llama3-8b-cn-ro-9773-v2/config.json from bucket guanaco-mkml-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/config.json from bucket guanaco-reward-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key rochatai-llama3-8b-cn-ro-9773-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.35s
rochatai-llama3-8b-cn-ro_9773_v2 status is now torndown due to DeploymentManager action